arXiv:2509.05323 · v3
Attention of a Kiss: Generative Video Attention Maps as Explainable and Creative Material
摘要
This paper presents an artistic and technical investigation into the attention mechanisms of video diffusion transformers. Inspired by early video artists who manipulated analog video signals to create new visual aesthetics, this study proposes a method for extracting and visualizing cross-attention maps in generative video models. Built on the open-source Wan model, our tool provides an interpretable window into the temporal and spatial behavior of attention in text-to-video generation. Through exploratory probes and a series of artistic case studies, we examine the potential of attention maps as both analytical tools and raw artistic material. This work contributes to the growing field of Explainable AI for the Arts (XAIxArts), inviting artists to reclaim the inner workings of AI as a creative medium.
作者备注:Under review for "Explainable AI for the Arts" (N. Bryan-Kinns, Ed.), Springer. The current version is an expanded book-chapter draft of our original XAIxArts 2025 workshop paper (ACM Creativity & Cognition 2025), available as v2 (arXiv:2509.05323v2)